Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aniketpanjwani/skills --skill landgit clone --depth 1 https://github.com/aniketpanjwani/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aniketpanjwani/skills/land)<a href="https://agentmods.dev/skills/aniketpanjwani/skills/land"><img src="https://agentmods.dev/badge/skills/aniketpanjwani/skills/land/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aniketpanjwani/skills/land"><img src="https://agentmods.dev/badge/skills/aniketpanjwani/skills/land.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00118 | $0.01512 |
| Opus 5 | $0.00059 | $0.00756 |
| Sonnet 5 | $0.00024 | $0.00302 |
| Haiku 4.5 | $0.00012 | $0.00151 |
Grade A, and why
land scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Land
Bare $land is a thin, direct git and gh workflow. The invocation itself
authorizes landing one obvious coherent scope; do not turn it into a review or
release-governance ceremony.
Thin default
A bare request such as “land,” “ship this,” “finish and merge,” or “wrap this
up” selects this path. It requires only git, authenticated GitHub CLI gh,
and the target repository's own hooks and validation.
1. Inspect and bound the scope
Use direct read-only git and gh commands to establish the repository,
GitHub remote, default branch, current branch or detached head, exact local
head, upstream, ahead/behind state, staged/unstaged/untracked paths, unpublished
commits, worktrees, and matching pull requests.
Proceed without another approval only when task context plus checkout evidence identifies exactly one obvious coherent scope. Preserve unrelated paths and existing commits. Reuse a matching pull request; never create a duplicate. A true no-op needs no mutation. Ambiguous or changed scope stops before mutation.
Do not run a Land-specific credential or secret scan. Repository-native hooks, push protection, and required hosted checks remain in force. Never bypass them. If ordinary inspection reveals a concrete credential, stop and report only its path and remediation need; never print its value.
2. Branch, commit, and validate once
Keep a suitable feature branch. If detached or on the default branch, create a feature branch from the work using the repository or host naming convention; never move another worktree to reclaim one.
Preserve existing commits and their separation. For one coherent uncommitted scope, stage only its exact paths and create one concise commit. Never amend, squash, reorder, or rewrite existing commits. Let repository-native commit hooks run; a hook failure stops the attempt without unrelated repair.
Reuse successful validation from this task only when it covered identical candidate content and nothing relevant changed. Otherwise run the repository's documented standard validation once. If none is declared, record that and rely on repository-native hooks plus required GitHub checks. Failure stops the path; do not fix, weaken, repeatedly rerun, or bypass validation while landing.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 139 lines · 118 tokens per session scan A db3e1e6e471e
land is a skill published in the GitHub repository aniketpanjwani/skills (52 stars, last pushed 24d ago), licensed MIT. It adds 118 tokens to every session and 1,512 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.